Hi Enrico, thanks for documenting and sharing your experience, happy to see that it's been largely positive, as has been my experience too.
I've been using ChatGPT in a professional coding capacity for visualization for the past year or so, best decision ever. I know people throw terms like 10x dev around.. but in terms of productivity I don't think it's an exaggeration. You've really nailed it with this article, especially the ultra mundane and gritty tasks like parsing text, counting occurences, matching dictionaries, it handles beautifully, and actually teaches more efficient/ pythonic ways of coding. But, I think the true power comes when you already have the expertise of knowing how to control all the different aspects of a plot, and know the specific language to refer to what you want, it makes far less errors when you remove ambiguity.
All in all I think it's changed the way I work from being a developer to more of a project manager. I have far more mental energy remaining to verify something it has written in 20 seconds based on a prompt, than I do to test functions I've spent 2 hours writing/debugging the artisan way. For that (more holistic/pragmatic) reason, I believe the quality of code is actually superior at the end of the day. Most of my visualization is done in Blender, a notoriously unintuitive programming interface with Python. I'm always blown away, so much that I rarely bother looking through my own codebase for what I've done before, always quicker and more performant to just regenerate as needed.
If you've ever seen 'the expanse', they have a natural language processing 3D visualization holograph computer, where the user prompts the computer to simulate celestial orbits and trajectories based on situation X. We're not *quite* there yet from high-level prompts to seamless visual output, but I think it's a valuable analogy for the role that Llama can play in modern visualization practice.
It's so interesting to hear what your experience was! Would you be interested in having a quick chat sometime? I'd love to learn more about your experience if you think you can carve out some time.
In particular, I'd be curious to hear what strategies you found for verification and maybe how your trust evolved over time.
Hi Enrico, thank you for your demonstration. I already don't have ChatGPT 4, but I will try to make some data visualizations as a test at the institution I'm doing my ethnography. If you have more ideas, please share with us! The students was asking how to teach data visualization using ChatGPT, so I think it will be a great opportunity to us to create a workshop. If you have any tip tu us, please, let me know!
Great article Enrico! I've only read it, not been able to watch the video yet, so apologies if you cover this in that, but I'm interested about the random dates it uses on the axis of the charts, was there any explanation for why it has not used month start or end dates when you have asked it to aggregate at the month level?
I have no idea. I have another version where I asked to have uniform dates, and it complied. In the session I recorded I believe I forgot to do it. Nice catch!
Hi Enrico, thanks for documenting and sharing your experience, happy to see that it's been largely positive, as has been my experience too.
I've been using ChatGPT in a professional coding capacity for visualization for the past year or so, best decision ever. I know people throw terms like 10x dev around.. but in terms of productivity I don't think it's an exaggeration. You've really nailed it with this article, especially the ultra mundane and gritty tasks like parsing text, counting occurences, matching dictionaries, it handles beautifully, and actually teaches more efficient/ pythonic ways of coding. But, I think the true power comes when you already have the expertise of knowing how to control all the different aspects of a plot, and know the specific language to refer to what you want, it makes far less errors when you remove ambiguity.
All in all I think it's changed the way I work from being a developer to more of a project manager. I have far more mental energy remaining to verify something it has written in 20 seconds based on a prompt, than I do to test functions I've spent 2 hours writing/debugging the artisan way. For that (more holistic/pragmatic) reason, I believe the quality of code is actually superior at the end of the day. Most of my visualization is done in Blender, a notoriously unintuitive programming interface with Python. I'm always blown away, so much that I rarely bother looking through my own codebase for what I've done before, always quicker and more performant to just regenerate as needed.
If you've ever seen 'the expanse', they have a natural language processing 3D visualization holograph computer, where the user prompts the computer to simulate celestial orbits and trajectories based on situation X. We're not *quite* there yet from high-level prompts to seamless visual output, but I think it's a valuable analogy for the role that Llama can play in modern visualization practice.
It's so interesting to hear what your experience was! Would you be interested in having a quick chat sometime? I'd love to learn more about your experience if you think you can carve out some time.
In particular, I'd be curious to hear what strategies you found for verification and maybe how your trust evolved over time.
So interesting!!!
Happily, I'll send you an email.
Thanks again!
"The artisan way" -- great term!
Hi Enrico, thank you for your demonstration. I already don't have ChatGPT 4, but I will try to make some data visualizations as a test at the institution I'm doing my ethnography. If you have more ideas, please share with us! The students was asking how to teach data visualization using ChatGPT, so I think it will be a great opportunity to us to create a workshop. If you have any tip tu us, please, let me know!
I am trying to learn how to do it effectively. I will keep reporting about my experience here. Thanks for your message!
Great article Enrico! I've only read it, not been able to watch the video yet, so apologies if you cover this in that, but I'm interested about the random dates it uses on the axis of the charts, was there any explanation for why it has not used month start or end dates when you have asked it to aggregate at the month level?
I have no idea. I have another version where I asked to have uniform dates, and it complied. In the session I recorded I believe I forgot to do it. Nice catch!
I think this illustrates just how descriptive you need to be with AI currently. Thanks for following up Enrico!
Yeah ... and also how careful you need to be! Having ways to notice problems and verify is a whole new (soft) skill to develop.